自然场景下的密集文本检测方法
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:


Dense Text Detection Method in Natural Scene
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 增强出版
  • |
  • 文章评论
    摘要:

    自然场景下的文本检测任务是图像处理领域中的难点之一. EAST (Efficient and Accurate Scene Text detector)算法是近年来比较出色的文本检测算法, 但是增加后置处理之后的AdvancedEAST算法仍存在由于激活像素的头尾边界丢失导致的漏检情况, 对密集文本的检测效果也不是很理想. 因此提出了Dilated-Corner Attention EAST (DCA_EAST)改进算法, 对网络结构加入空洞卷积模块以及角点注意力模块, 改善了漏检情况. 针对损失函数, 加入类别权重因子和样本难度权重因子, 有效提升了密集文本的检测效果. 实验结果表明, 该算法在ICDAR2019的ReCTS数据集上准确率为93.02%, 召回率为76.69%, F-measured值为84.07%, 优于AdvancedEAST算法.

    Abstract:

    Text detection in natural scenes is one of the difficulties in the field of image processing. An efficient and accurate scene text detector (EAST) algorithm is an excellent text detection algorithm in recent years, but the AdvancedEAST algorithm after the addition of post processing still has the problem of missed detection caused by the loss of the head and tail boundaries of the activated pixels. Thus, the detection effect of dense texts is not ideal. For this reason, an improved algorithm of dilated-corner attention EAST (DCA_EAST) is proposed, and a dilated convolution module and a corner attention module are added to the network structure to improve the missed detection. For the loss function, weight factors of category and sample difficulty are introduced to effectively improve the detection effect of dense texts. The experimental results show that the proposed algorithm has an accuracy of 93.02%, a recall rate of 76.69%, and an F-measured value of 84.07% on the ReCTS dataset of ICDAR2019, thus being superior to the AdvancedEAST algorithm.

    参考文献
    相似文献
    引证文献
引用本文

牟森,陈洪刚,卿粼波,何小海,王思怡.自然场景下的密集文本检测方法.计算机系统应用,2021,30(2):171-175

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-06-18
  • 最后修改日期:2020-07-14
  • 录用日期:
  • 在线发布日期: 2021-01-29
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号